© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 224890
    Prev
    Next
    INDEX
    Explanations

    stock units

    np_acts-logits-general · gemini-2.5-flash-lite

    register: variable assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Moore
    0.44
     देहरादून
    0.44
    ESPN
    0.44
    "/"
    0.43
     ausdr
    0.41
     Patten
    0.41
     ক্ষমা
    0.41
    挠
    0.41
    expressed
    0.40
     Worcestershire
    0.40
    POSITIVE LOGITS
     was
    0.54
     actors
    0.49
     asteroids
    0.49
     nymphs
    0.49
     fue
    0.49
     vouchers
    0.48
    は
    0.48
     corals
    0.47
     planets
    0.47
     widgets
    0.47
    Activations Density 0.001%

    No Known Activations